Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers followed by zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁷
    0.84
     sixteen
    0.84
     seventeen
    0.81
     seven
    0.81
     nineteen
    0.80
     Eight
    0.80
     thirteen
    0.79
     eleven
    0.78
     Fourteen
    0.78
     Sixteen
    0.77
    POSITIVE LOGITS
    0
    1.53
    ۰
    1.35
    ០
    1.32
    ০
    1.28
    ０
    1.27
    ०
    1.22
    ٠
    1.19
    𝟬
    1.12
    ૦
    1.09
    ୦
    1.09
    Act Density 0.657%

    No Known Activations